Neural Audio Coding with Linear Filters for Low-Bitrate Speech

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing linear predictive-based codecs struggle to meet the requirements of delivering high-quality speech coding at low bit-rates with low complexity and low memory, while neural network-based codecs are resource-intensive and computationally expensive.

Innovation Solution

Combining a non-linear source generated by a first machine learning system with a linear filter estimated by a second machine learning system, such as neural networks, to perform audio coding, reducing complexity and enhancing quality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If neural network-based codecs are used, then audio quality is improved, but computational complexity and resource requirements increase

Engineering Contradiction:
Improveaudio qualityVSAvoidcomputational complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The audio coding system is segmented into two independent neural network components: one dedicated to generating the excitation signal and another dedicated to generating the filter parameters. This segmentation allows each component to be optimized separately and processed independently, reducing the overall computational burden while maintaining high audio quality through specialized processing in each segment.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The invention extracts and separates the traditionally coupled processes of excitation signal generation and filter parameter generation into distinct neural network modules. By taking out these functions and processing them separately, the system achieves better computational efficiency and resource utilization while preserving the high-quality audio reconstruction capability.

Inventive Principle:
Principle #2Taking out (Extraction)

2Device complexity

If linear predictive-based codecs are used, then computational complexity is reduced, but audio quality deteriorates

Engineering Contradiction:
Improvecomputational complexityVSAvoidaudio quality
Core Design Contradiction:
Device complexityVSManufacturing precision

Solution Approach 1:

The invention replaces traditional mechanical linear predictive coding algorithms with neural network-based models for generating excitation signals and filter parameters. This substitution introduces non-linear processing capabilities that significantly improve audio quality while maintaining computational efficiency through the inherent parallel processing capabilities of neural networks.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system combines the strengths of traditional linear predictive coding (efficient filter structure) with neural network capabilities (non-linear signal processing) to create a hybrid audio coding system. This composite approach leverages the computational efficiency of linear models while incorporating the quality-enhancing non-linear processing of neural networks.

Inventive Principle:
Principle #40Composite materials

3Manufacturing precision

If high bit-rates are used, then audio quality is improved, but data transmission requirements increase

Engineering Contradiction:
Improveaudio qualityVSAvoidbit-rate
Core Design Contradiction:
Manufacturing precisionVSQuantity of substance

Solution Approach 1:

The invention changes the parameter representation by using neural networks to generate compact excitation signals and filter parameters that capture the essential characteristics of the audio signal. This parameter transformation enables high-quality audio reconstruction at lower bit-rates by efficiently encoding the most important signal features.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The neural network-based excitation signal generator creates a compact representation that copies the essential characteristics of the original audio signal's excitation component. This efficient copying mechanism allows for high-fidelity audio reconstruction using significantly fewer bits compared to traditional methods.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4416726B1Audio coding using machine learning based linear filters and non-linear neural sources
Publication Date: 2026.03.04 QUALCOMM INC
  • EP4416726B1 patent drawingFigure 1
  • EP4416726B1 patent drawingFigure 2
  • EP4416726B1 patent drawingFigure 3

AI summary

Systems and techniques are described for coding audio signals. For example, a voice decoder can generate, using a first neural network, an excitation signal for at least one sample of an audio signal at least in part by performing a non-linear operation based on one or more inputs to the first neural network, the excitation signal being configured to excite a learned linear filter. The voice decoder can further generate, using the learned linear filter and the excitation signal, at least one sample of a reconstructed audio signal. For example, a second neural network can be used to generate coefficients for one or more learned linear filters, which receive as input the excitation signal generated by the first neural network trained to perform the non-linear operation.